Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Segmentation into three classes using gradients.

S S Trivedi, G T Herman, J K Udupa

    IEEE Transactions on Medical Imaging
    |January 1, 1986
    PubMed
    Summary
    This summary is machine-generated.

    Related Concept Videos

    You might also read

    Related Articles

    Articles linked to this work by shared authors, journal, and citation graph.

    Sort by
    Same author

    Anatomic attention regions via optimal anatomy modeling and recognition for DL-based image segmentation.

    Proceedings of SPIE--the International Society for Optical Engineering·2024
    Same author

    Optimal computed tomography-based biomarkers for prediction of incisional hernia formation.

    Hernia : the journal of hernias and abdominal wall surgery·2023
    Same author

    Endothelial nitric oxide synthase (eNOS) gene Glu298Asp polymorphism and expression in North Indian preeclamptic women.

    Pregnancy hypertension·2015
    Same author

    Arterio-venous malformations of uterus - diagnostic and management dilemmas.

    Journal of obstetrics and gynaecology : the journal of the Institute of Obstetrics and Gynaecology·2014
    Same author

    Hepatitis B vaccination with or without hepatitis B immunoglobulin at birth to babies born of HBsAg-positive mothers prevents overt HBV transmission but may not prevent occult HBV infection in babies: a randomized controlled trial.

    Journal of viral hepatitis·2013
    Same author

    Three-dimensional kinematic stress magnetic resonance image analysis shows promise for detecting altered anatomical relationships of tissues in the cervical spine associated with painful radiculopathy.

    Medical hypotheses·2013
    Same journal

    Physiology-guided Self-supervised Learning for Simultaneous Dual-Tracer PET Separation.

    IEEE transactions on medical imaging·2026
    Same journal

    Informed-Exploration Reinforcement Learning for Automated Virtual Coronary Intervention Planning.

    IEEE transactions on medical imaging·2026
    Same journal

    4D Reconstruction of Fetal Left Ventricle from Echocardiography via 2.5D Radial Segmentation and Graph-Fourier Reconstruction.

    IEEE transactions on medical imaging·2026
    Same journal

    Generalised Medical Phrase Grounding.

    IEEE transactions on medical imaging·2026
    Same journal

    EndoLRMGS: Combining Large Reconstruction Modelling and Gaussian Splatting for Complete Endoscopic Scene Reconstruction.

    IEEE transactions on medical imaging·2026
    Same journal

    A Neural-Analytical Fusion Scatter Correction Method for Multi-Source CT Using Equivalent High-Order Scatter.

    IEEE transactions on medical imaging·2026
    See all related articles

    Partial volume artifact in 3D imaging can obscure tissue boundaries. A new method uses gradient and density in feature space to accurately segment tissues, improving medical image analysis.

    Area of Science:

    • Medical Imaging
    • Image Processing
    • Computational Anatomy

    Background:

    • Discretized 3D scenes assign average density to voxels.
    • Partial volume artifact occurs at class interfaces, causing misclassification.
    • Voxels with mixed densities (Class 1 and 3) resemble Class 2 voxels based on density alone.

    Purpose of the Study:

    • To develop a novel method for segmenting discrete 3D scenes.
    • To overcome limitations of density-based segmentation caused by partial volume artifact.
    • To enable meaningful three-class segmentation in medical imaging.

    Main Methods:

    • Utilizing a two-dimensional feature space combining gradient and density.
    • Applying this feature space to segment voxels into three distinct classes.

    Related Experiment Videos

  • Illustrating the method with practical examples from medical imaging.

    • Main Results:

    • Demonstrated effective segmentation of scenes with partial volume artifact.
    • Successfully distinguished voxels at class interfaces from homogeneous voxels.
    • Provided a robust approach for three-class segmentation in medical imaging.

    Conclusions:

    • The gradient-density feature space method effectively addresses partial volume artifact.
    • This approach enables more accurate and meaningful segmentation of medical images.
    • The technique offers significant improvements for analyzing complex 3D data.